Struct MultimodalInputs 

pub struct MultimodalInputs {
    pub mm_items: Vec<MultimodalDataItem>,
    pub im_token_id: Option<i64>,
    pub video_token_id: Option<i64>,
    pub mrope_positions: Option<Tensor>,
    pub mrope_position_delta: Option<Tensor>,
    pub mrope_position_delta_scalar: Option<i64>,
    pub mrope_position_delta_repeated_cache: Option<Tensor>,
}

The multimodal part of a request.

Fields

mm_items: Vec<MultimodalDataItem>

The media items, in prompt order.

im_token_id: Option<i64>

Image placeholder token id.

video_token_id: Option<i64>

Video placeholder token id.

mrope_positions: Option<Tensor>

M-RoPE position ids.

mrope_position_delta: Option<Tensor>

M-RoPE position delta.

mrope_position_delta_scalar: Option<i64>

M-RoPE position delta as a scalar.

mrope_position_delta_repeated_cache: Option<Tensor>

Retired slot kept for arity; always None.

Trait Implementations

impl Clone for MultimodalInputs

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MultimodalInputs

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for MultimodalInputs

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for MultimodalInputs

impl Wire for MultimodalInputs

fn encode(&self, encoder: &mut Encoder)

Append this value to a message.

fn decode(decoder: &mut Decoder<'_>) -> Result<Self>

Read one value of this type.